Patent Issued for Commercial claim processing platform using machine learning to generate shared economy insights (USPTO 11798095): Allstate Insurance Company

2023 NOV 14 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent by the inventors Brune, Nathan (Chicago, IL, US), Deans, John (Northbrook, IL, US), Gore, Matthew (Chicago, IL, US), Gutsell, Christopher Paul (Gurnee, IL, US), Harasymczuk, Rebecca (Chicago, IL, US), Kelsh, John P. (Antioch, IL, US), filed on March 29, 2021, was published online on October 24, 2023, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents.

Patent number 11798095 is assigned to Allstate Insurance Company (Northbrook, Illinois, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “Aspects of the disclosure relate to enhanced processing systems for executing machine learning algorithms and providing insights for commercial and/or shared economy services. Many organizations and/or individuals make claims related to commercial incidents (e.g., relating to work, employees, or the like). In some instances, however, these claims might not be optimally processed for organizations providing commercial and/or shared economy services, which may result in excessive expenditure of resources for both shared economy organizations and others.”

In addition to the background information obtained for this patent, NewsRx journalists also obtained the inventors’ summary information for this patent: “Aspects of the disclosure provide effective, efficient, scalable, and convenient technical solutions that address and overcome the technical problems associated with generation of commercial and shared economy insights.

“In accordance with one or more embodiments, a computing platform comprising at least one processor, a communication interface communicatively coupled to the at least one processor, and memory may receive historical claim processing information. The computing platform may train a machine learning model using the historical claim processing information, which may configure the machine learning model to output new claim processing information based on claim information. The computing platform may receive a new claim, including claim information. Using the machine learning model, the computing platform may process the new claim, which may result in the new claim processing information. The computing platform may send, to a user computing device, the new claim processing information and one or more commands directing the user computing device to display the new claim processing information, which may cause the user computing device to display the new claim processing information.

“In one or more instances, the historical claim processing information may include one or more of: one or more images, one or more videos, damage assessment information, fault information, settlement amounts, telematics data, and/or other information. In one or more instances, the computing platform may compare the new claim processing information to a predetermined confidence threshold. Based on identifying that the new claim processing information exceeds the predetermined confidence threshold, the computing platform may send the new claim processing information to the user computing device without manual review. Based on identifying that the new claim processing information does not exceed the predetermined confidence threshold, the computing platform may send the new claim processing information for manual review.

“In one or more examples, the computing platform may generate, while processing the new claim, claim status information indicating a status of processing the new claim. The computing platform may receive a request for a status update for processing of the new claim. In response to the request for the status update, the computing platform may send the claim status information, which may cause the claim status information to be displayed at a remote computing device.

“In one or more instances, sending, to the user computing device, the new claim processing information and one or more commands directing the user computing device to display the new claim processing information may include sending, via an enterprise computing system, the new claim processing information and the one or more commands directing the user computing device to display the new claim processing information. In these instances, the enterprise computing system may be configured to render the new claim processing information for display.”

The claims supplied by the inventors are:

“1. A computing platform comprising: at least one processor; a communication interface communicatively coupled to the at least one processor; and memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to: train a machine learning model comprising a plurality of sub-models by using historical claim processing information, wherein training the machine learning model comprises: receiving an input comprising one of a query or a new claim, wherein if the input is the query: train the machine learning model to identify a first one or more sub-models of the plurality of sub-models as being associated with the query; generate, using the first one or more sub-models, insight information in response to the query; and send, to a user computing device, the insight information and one or more commands directing the user computing device to display the insight information, wherein sending the one or more commands causes the user computing device to display the insight information; or if the input is the new claim: train the machine learning model to identify a second one or more sub-models of the plurality of sub-models as being associated with the new claim; process, using the second one or more sub-models the new claim, wherein processing the new claim comprises: comparing, using the second one or more sub-models, new claim information and the stored historical claim processing information; generating, using the second one or more sub-models, a plurality of decisions in response to the comparison of the new claim information and the stored historical claim processing information; generating, using the second one or more sub-models, new claim processing information comprising a recommendation based on the plurality of decisions; generating a match score based on a comparison of the new claim processing information to the historical claim processing information comparing the match score to a predetermined confidence threshold; and based on identifying that the match score exceeds the predetermined confidence threshold, sending, to the user computing device, the new claim processing information and one or more commands directing the user computing device to display the new claim processing information, wherein sending the one or more commands causes the user computing device to display the new claim processing information.

“2. The computing platform of claim 1, wherein the historical claim processing information includes one or more of: one or more images, one or more videos, damage assessment information, fault information, settlement amounts, or telematics data.

“3. The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to: based on identifying that the new claim processing information does not exceed the predetermined confidence threshold, designate the new claim processing information for manual review.

“4. The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to: generate, while processing the new claim, claim status information indicating a status of processing the new claim; receive a request for a status update for processing of the new claim; and send, in response to the request for the status update, the claim status information, wherein sending the claim status information causes the claim status information to be displayed at a remote computing device.

“5. The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to: receive, from the user computing device, confirmation information; and in response to receiving the confirmation information, perform one or more of: sending one or more commands comprising instructions for an event processing system to execute a payment corresponding to the new claim, or sending one or more commands comprising instructions for a third party service device to cause dispatch of a service vehicle based on the claim information.

“6. The computing platform of claim 1, wherein the plurality of decisions comprises a damage assessment, a fault assessment, and an injury assessment.

“7. The computing platform of claim 1, wherein the query is a request for one of: a damage assessment, a fault assessment, or an injury assessment.

“8. The computing platform of claim 1, wherein the comparison of the new claim processing information to the historical claim processing information is based on at least one of a damage type, vehicle type, and a geographic region.

“9. The computing platform of claim 1, wherein training the machine learning model further comprises: determining the new claim information is insufficient to process the new claim; and in response to determining the new claim information is insufficient: requesting additional claim information from the user computing device; or contacting an insurance adjuster.

“10. A method comprising: at a computing platform comprising at least one processor, a communication interface, and memory: training a machine learning model comprising a plurality of sub-models by using historical claim processing information, wherein training the machine learning model comprises: receiving an input comprising one of a query or a new claim, wherein if the input is the query; training the machine learning model to identify a first one or more sub-models of the plurality of sub-models as being associated with the query; generating, using the first one or more sub-models, insight information in response to the query; and sending, to a user computing device, the insight information and one or more commands directing the user computing device to display the insight information, wherein sending the one or more commands causes the user computing device to display the insight information; or if the input is the new claim: training the machine learning model to identify a second one or more sub-models of the plurality of sub-models as being associated with the new claim: generating, using the second one or more sub-models, new claim processing information comprising a recommendation; generating, while processing the new claim, claim status information indicating a status of processing the new claim; receiving a request for a status update for processing of the new claim; sending, in response to the request for the status update, the claim status information, wherein sending the claim status information causes the claim status information to be displayed at a remote computing device; generating a match score based on a comparison of the new claim processing information to the historical claim processing information; comparing the match score to a predetermined confidence threshold; and based on identifying that the match score exceeds the predetermined confidence threshold, sending, once the claim has been processed and to the user computing device, the new claim processing information and one or more commands directing the user computing device to display the new claim processing information, wherein sending the one or more commands causes the user computing device to display the new claim processing information.

“11. The method of claim 10, wherein the historical claim processing information includes one or more of: one or more images, one or more videos, damage assessment information, fault information, settlement amounts, or telematics data.

“12. The method of claim 10, further comprising: based on identifying that the new claim processing information does not exceed the predetermined confidence threshold, designating the new claim processing information for manual review.

“13. The method of claim 10, further comprising: receiving, from the user computing device, confirmation information; and in response to receiving the confirmation information, performing one or more of: sending one or more commands comprising instructions for an event processing system to execute a payment corresponding to the new claim, or sending one or more commands comprising instructions for a third party service device to cause dispatch of a service vehicle based on the claim information.

“14. The method of claim 10, wherein the query is a request for one of: a damage assessment, a fault assessment, or an injury assessment.

“15. The method of claim 10, wherein the comparison of the new claim processing information to the historical claim processing information is based on at least one of a damage type, vehicle type, and a geographic region.”

There are additional claims. Please visit full patent to read further.

URL and more information on this patent, see: Brune, Nathan. Commercial claim processing platform using machine learning to generate shared economy insights. U.S. Patent Number 11798095, filed March 29, 2021, and published online on October 24, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11798095)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)